Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptors that convey admiration or aesthetic appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riteria
    -0.14
    ervas
    -0.14
    ythe
    -0.14
    elon
    -0.13
    .FontStyle
    -0.13
    shaw
    -0.13
    resh
    -0.13
    ouver
    -0.13
     attenu
    -0.13
    owa
    -0.13
    POSITIVE LOGITS
     Hed
    0.21
     oneself
    0.18
     hed
    0.17
     itself
    0.16
    cha
    0.16
    .gdx
    0.15
    presentation
    0.15
     themselves
    0.15
     captures
    0.15
     thems
    0.14
    Act Density 0.000%

    No Known Activations